Can generative AI craft scale items? A mixed-method study on AI's capability to adapt and create new scales with recommendations for best practices
Year: 2025
Type: article
Abstract: This study explores the potential of generative artificial intelligence (AI), specifically Generative Pre-trained Transformer 4 (GPT-4), in revolutionizing the development and adaptation of research scales, a process traditionally characterized by its time-intensive nature and susceptibility to human bias. Employing a mixed-method approach, the study assesses GPT-4’s ability to generate reliable and valid scales, comparing them to conventional methods. After testing various generative AI models, GPT-4 was chosen for its accessibility and accuracy in producing contextually appropriate items. Quantitative analysis confirmed the AI-generated scales’ reliability and validity, while expert evaluations highlighted the model’s ability to enhance methodological efficiency and reduce bias. However, the study underscores the importance of combining AI’s computational strengths with human expertise to ensure optimal outcomes. By integrating generative AI into scale development, this research introduces innovative practices that streamline the process without compromising quality. The findings pave the way for future exploration of AI’s role in research methodologies, offering recommendations for best practices in using AI for scale development. This study contributes to the broader discourse on AI’s transformative potential in research, emphasizing its capacity to enhance the precision and efficiency of data collection tools.
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $1,180
OpenAlex ID: W4411860931